Compare / gemini-3-pro-preview vs Kimi K2.5

gemini-3-pro-preview vs Kimi K2.5

6 results from 3 sources that measured both models. Each row is in the source's own units; there is no overall winner.

gemini-3-pro-preview
Google · profile
Kimi K2.5
Moonshot AI · profile
Results compared
6
Shared sources
3
BenchmarkMetricgemini-3-pro-previewKimi K2.5
UGI LeaderboardreportedRequested-length error% off the requested word count 33.0%10.0%
UGI LeaderboardreportedStyle adherencescore from 0 to 1 0.370.34
UGI LeaderboardreportedWriting scorescore out of 100 66.762.4
Vectara Hallucination LeaderboardreportedAnswer rate% of documents 99.4%92.2%
Vectara Hallucination LeaderboardreportedHallucination rate% of summaries 13.6%14.2%
Vending-Bench 2reportedMoney after a yearUS dollars $5,478.16$1,198.46

Bold green marks the better value on that metric. Where a source reports ranges that overlap, the difference may not be meaningful; see the benchmark page for ranges.